© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 78930
    Prev
    Next
    INDEX
    Explanations

    references to Middle Eastern countries involved in conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ackle
    -0.06
     lip
    -0.06
     Bris
    -0.06
     vene
    -0.06
    hom
    -0.06
    izzo
    -0.06
     Masters
    -0.05
     Vict
    -0.05
     Urb
    -0.05
     pen
    -0.05
    POSITIVE LOGITS
    sse
    0.07
    gmt
    0.07
    -transitional
    0.07
    #ad
    0.07
    ç̬
    0.06
    otte
    0.06
    ìĹĩ
    0.06
    /fontawesome
    0.06
    .aw
    0.06
     Angiospermae
    0.06
    Activations Density 0.047%

    No Known Activations